© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30827
    Prev
    Next
    INDEX
    Explanations

    NAME_1 followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="{!!
    -0.09
    GGLE
    -0.09
     Bernard
    -0.09
    oton
    -0.09
    .BLL
    -0.09
    aphore
    -0.08
     Vine
    -0.08
    ERNEL
    -0.08
    adients
    -0.08
    SCRIPTOR
    -0.08
    POSITIVE LOGITS
    âĢ³
    0.20
    âĢ²
    0.17
    aeda
    0.11
    morgan
    0.10
     Rodrigo
    0.10
    IBUT
    0.10
    éĥİ
    0.09
    WithMany
    0.09
    Radians
    0.09
    ï¸ı
    0.09
    Activations Density 0.142%

    No Known Activations